Text Understanding With Multiple Knowledge Sources: An Experiment in Distributed Parsing

TEXT UNDERSTANDING WITH MULTIPLE KNOWLEDGE SOURCES: AN EXPERIMENT IN DISTRIBUTED PARSING Cinzia Costantini, Danilo Fum, Giovanni Guida, Angelo Montanad, Carlo Tasso Laboratorio di Intelligenza Artificiale Dipartimento di Matematica e Informatica Universita' di Udine Udine, italy ABSTRACT A novel approach to the problem of text understanding is presented, which exploits a distributed processing concept, where knowledge from different sources comes into play in the course of comprehension. In the paper the rationale of advocating such an approach and the.advantages in following it are discussed. A proto- type parser based on an original distributed problem-solving archi- tecture is presented. It encompasses a centralized declarative con- trol module and a collection of decentralized, loosely coupled, heterogeneous problem solvers specialized in the vadous facets of the parsing task. The mechanisms of coordination and communica- tion among the specialists are illustrated, and an example of the parser operation is given. The parser is implemented in LISP on a SUN workstation. 1. INTRODUCTION The processes underlying text understanding involve a variety of complex, multifaceted activities which have not been yet completely understood from the cognitive point of view, and which still lack adequate computational models. Recent research trends in cogni- tive science and artificial intelligence, however, have put forward some ideas conoeming human cognition and automatic problem solving that offer promising tools for the design of text understand- ing systems. One of the key ideas emerged in the field of cognitive study of natural language comprehension is that text understanding consti- tutes in humans an interactive process, where bottom-up, data- driven activities combine with top-down, expectation-driven ones to cooperatively determine the most I~ely interpretation of the input (Lesgoid and Perfetti, 1981). Roughly speaking, humans begin with a set of expectations about what information is likely to be found in the text. These expectations are based both on linguistic knowledge (about words, phrases, sentences, and larger pieces of discourse) and on non-linguistic world knowledge. As information from the text becomes available, the reader strengthens those hypotheses that are consistent with the input and weakens those that are inconsistent. The stronger hypotheses, in turn, make even more specific predictions about the information represented in the text, so as the initial expectations are successively corrected and refined until they eventually yield an adequate approximation of the meaning of the text. In one of the first and mere detailed descriptions of interactive processes in text understanding, Rumelhart (1977) has proposed a model comprising several knowledge sources, each one operating independently and in parallel with the others. These knowledge sources are processors operating at different levels of linguistic representation. The outputs of each of these knowledge sources are hypotheses or best guesses from the data available at that level. The hypotheses are transferred to a central device, called the message center, where they can be observed by all other knowledge sources, thus being available as evidence for or against hypotheses at other levels. In a more dynamic view of interaction, Levy (1981) suggests that the message center could modify the activity …

Content truncated to 500 words